© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 24583
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erat
    -0.08
    elim
    -0.07
    Äįin
    -0.07
    essa
    -0.06
    own
    -0.06
    æľīæĿ¡
    -0.06
    Latch
    -0.06
     privilégi
    -0.06
    -type
    -0.06
    apt
    -0.06
    POSITIVE LOGITS
    eters
    0.09
    约åIJĪ
    0.09
     اÙĦÙĪاØŃد
    0.07
    emente
    0.07
    /year
    0.07
    æĬĺåIJĪ
    0.07
    мок
    0.07
     brutto
    0.07
    /month
    0.07
     assorted
    0.07
    Activations Density 0.048%

    No Known Activations